INDEX

Explanations

mentions of the word "her" in various contexts

oai_token-act-pair · gpt-3.5-turbo

the repeated use of the word "her."

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

CCC

-0.65

ouls

-0.64

sew

-0.62

 rolling

-0.58

 transformer

-0.58

RAW

-0.57

 trim

-0.56

 caps

-0.56

 Bulk

-0.56

govtrack

-0.56

POSITIVE LOGITS

itage

1.55

ding

1.10

itance

1.02

ald

0.98

der

0.97

tz

0.97

rha

0.96

jee

0.93

pes

0.90

rer

0.90

Activations Density 0.021%

mentions of the word "her" in various contexts

the repeated use of the word "her."

No Comments

No Known Activations